Podcast Episodes
Back to Search“AI catastrophes and rogue deployments” by Buck
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.[Thanks to Aryan Bhatt, Ansh Radhakrishnan, Adam Kaufman, Vivek…
2 years, 2 months ago
“Loving a world you don’t trust” by Joe Carlsmith
(Cross-posted from my website. Audio version here, or search for "Joe Carlsmith Audio" on your podcast app.)
This is the final essay in a series that …
2 years, 2 months ago
“LLM Generality is a Timeline Crux” by eggsyntax
Summary Summary .
LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible.
Longer summary
Ther…
2 years, 2 months ago
“LLM Generality is a Timeline Crux” by eggsyntax
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short Summary
LLMs may be fundamentally incapable of fully gene…
2 years, 3 months ago
“LLM Generality is a Timeline Crux” by eggsyntax
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual. Short Summary
LLMs may be fundamentally incapable of fully gene…
2 years, 3 months ago
“Formal verification, heuristic explanations and surprise accounting” by paulfchristiano
ARC's current research focus can be thought of as trying to combine mechanistic interpretability and formal verification. If we had a deep understand…
2 years, 3 months ago
“LLM Generality is a Timeline Crux” by eggsyntax
Summary Summary .
LLMs may be fundamentally incapable of fully general reasoning, and if so, short timelines are less plausible.
Longer summary
Ther…
2 years, 3 months ago
“SAE feature geometry is outside the superposition hypothesis” by jake_mendel
Summary: Superposition-based interpretations of neural network activation spaces are incomplete. The specific locations of feature vectors contain cr…
2 years, 3 months ago
“Connecting the Dots: LLMs can Infer & Verbalize Latent Structure from Training Data” by Johannes Treutlein, Owain_Evans
Crossposted from the AI Alignment Forum. May contain more technical jargon than usual.This is a link post.TL;DR: We published a new paper on out-of-c…
2 years, 3 months ago
“Boycott OpenAI” by PeterMcCluskey
This is a link post.I have canceled my OpenAI subscription in protest over OpenAI's lack ofethics.
In particular, I object to:
threats to confiscate d…
2 years, 3 months ago